In this project we trained a chatbot using movie scripts from the Cornell Movie-Dialogs Corpus. We built multi-domain generative conversational model for teaching a machine to carry out a meaningful conversation with a human in multiple domains.
> hello?
Bot: hello .
> where am I?
Bot: you re in a hospital .
> who are you?
Bot: i m a lawyer .
> how are you doing?
Bot: i m fine .
> are you my friend?
Bot: no .
> you're under arrest
Bot: i m trying to help you !
> i'm just kidding
Bot: i m sorry .
> where are you from?
Bot: san francisco .
> it's time for me to leave
Bot: i know .
> goodbye
Bot: goodbye .- Python
- PyTorch
- Data loading and preprocessing
- Recurrent sequence-to-sequence model
- Encoder model
- Decoder model
- Greedy-search decoding